Source: https://seerepo.com/compare/harvard-edge/cs249r_book/vs/liguodongiot/llm-action
Markdown source: https://seerepo.com/compare/harvard-edge/cs249r_book/vs/liguodongiot/llm-action.md
Description: cs249r_book and llm-action share 43 technologies: pyzmq, pyarrow, jupyter-core, jupyterlab-server, tornado, cycler, fonttools, jupyterlab-pygments, soupsieve, tinycss2, contourpy, matplotlib-inline, prompt-toolkit, seaborn, matplotlib, argon2-cffi, argon2-cffi-bindings, torch, transformers, torchvision, scikit-learn, librosa, nltk, bleach, defusedxml, jinja2, markdown-it-py, markupsafe, mdurl, mistune, nbconvert, pandocfilters, webencodings, beautifulsoup4, pillow, lxml, jupytext, nbformat, fastjsonschema, Pydantic, jsonschema, prometheus-client, and psutil. cs249r_book is written in Python and llm-action in HTML.

# cs249r_book vs llm-action

cs249r_book and llm-action share 43 technologies: pyzmq, pyarrow, jupyter-core, jupyterlab-server, tornado, cycler, fonttools, jupyterlab-pygments, soupsieve, tinycss2, contourpy, matplotlib-inline, prompt-toolkit, seaborn, matplotlib, argon2-cffi, argon2-cffi-bindings, torch, transformers, torchvision, scikit-learn, librosa, nltk, bleach, defusedxml, jinja2, markdown-it-py, markupsafe, mdurl, mistune, nbconvert, pandocfilters, webencodings, beautifulsoup4, pillow, lxml, jupytext, nbformat, fastjsonschema, Pydantic, jsonschema, prometheus-client, and psutil. cs249r_book is written in Python and llm-action in HTML.

- [harvard-edge/cs249r_book](https://seerepo.com/r/harvard-edge/cs249r_book): Machine Learning Systems: Foundations, Scaling, Agentic AI, and Physical AI (Vols I–IV) • Harvard CS249r | https://mlsysbook.ai
- [liguodongiot/llm-action](https://seerepo.com/r/liguodongiot/llm-action): 本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

## What they share and what sets them apart

- In common: pyzmq, pyarrow, jupyter-core, jupyterlab-server, tornado, cycler, fonttools, jupyterlab-pygments, soupsieve, tinycss2, contourpy, matplotlib-inline, prompt-toolkit, seaborn, matplotlib, argon2-cffi, argon2-cffi-bindings, torch, transformers, torchvision, scikit-learn, librosa, nltk, bleach, defusedxml, jinja2, markdown-it-py, markupsafe, mdurl, mistune, nbconvert, pandocfilters, webencodings, beautifulsoup4, pillow, lxml, jupytext, nbformat, fastjsonschema, Pydantic, jsonschema, prometheus-client, psutil
- Only in cs249r_book: async-lru, flexcache, requests-cache, anyio, marimo, Vite, React, idb, Next.js, ipywidgets, jupyter-server-terminals, jupyterlab-widgets, widgetsnbextension, Rich, Plotly, groq, Ollama, OpenAI, tflite, sentence-transformers, ogb, torch-geometric, betterbib, ghostscript, latexcodec, pybtex, pylatexenc, pypandoc, python-frontmatter, sgf, tablib, xlrd, xlwt, xmltodict, epubcheck, bibtexparser, annotated-types, cattrs, fqdn, jsonschema-specifications, linkml, referencing, rfc3339-validator, rfc3986-validator, rfc3987-syntax, linkml-runtime, python-json-logger, Tailwind CSS, Chart.js, D3, Mermaid, ink-mde, compromise, dompurify, katex, markdown-it, markdown-it-container, jspdf, jspdf-autotable, Framer, react-medium-image-zoom, Lucide
- Only in llm-action: partd, pickleshare, s3transfer, smart-open, tensorboard-data-server, zict, AIOHTTP, apex, werkzeug, Google, google-auth-oauthlib, oauthlib, requests-oauthlib, cuda-python, cupy-cuda12x, deepspeed, flash-attn, langdetect, llvmlite, ONNX, polygraphy, pycocotools, rouge-score, sentencepiece, spaCy, spacy-legacy, tensorrt, thinc, tokenizers, torchtext, transformer-engine, triton, xgboost, bs4, feedparser, markdown, mdit-py-plugins, newspaper3k, sgmllib3k, execnet, spacy-loggers, boto3, botocore

## Side by side

| | cs249r_book | llm-action |
|---|---|---|
| Size | 828,618 lines written, 1,983 code files | 23,875 lines written, 10 code files |
| Who writes it | 2.7% of its commits signed by AI. With Codex, Claude Code, and Cursor | 0% of its commits signed by AI |
| Activity | Last push November 15, 2026, 22,406 commits, 30,209 stars | Last push October 14, 2026, 945 commits, 25,281 stars |
| Tests | 632 test files. 16.8% of its code files have a test that imports them | 1 test files |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, cs249r_book or llm-action?

cs249r_book, with 828,618 lines written; llm-action has 23,875.

The proof: [harvard-edge/cs249r_book's code at commit 5b6b3c8](https://github.com/harvard-edge/cs249r_book/tree/5b6b3c8d82e429ea25c9c04dd1be477937008c28)

### Which has more GitHub stars, cs249r_book or llm-action?

cs249r_book, with 30,209 stars; llm-action has 25,281.

The proof: [harvard-edge/cs249r_book on GitHub](https://github.com/harvard-edge/cs249r_book)

### Which has more tests, cs249r_book or llm-action?

cs249r_book, with 632 test files; llm-action has 1.

The proof: [harvard-edge/cs249r_book's code at commit 5b6b3c8](https://github.com/harvard-edge/cs249r_book/tree/5b6b3c8d82e429ea25c9c04dd1be477937008c28)

### Which was updated more recently, cs249r_book or llm-action?

cs249r_book: its last push was on November 15, 2026, and llm-action's on October 14, 2026.

The proof: [harvard-edge/cs249r_book's commits on GitHub](https://github.com/harvard-edge/cs249r_book/commits)

### Which has more commits signed by AI, cs249r_book or llm-action?

cs249r_book: an AI signed 2.7% of its commits, with Codex, Claude Code, and Cursor.

The proof: [the commits each tool signed in harvard-edge/cs249r_book](https://seerepo.com/r/harvard-edge/cs249r_book/ai)

## Sources

- harvard-edge/cs249r_book: Read on November 15, 2026, at commit 5b6b3c8 (https://github.com/harvard-edge/cs249r_book/tree/5b6b3c8d82e429ea25c9c04dd1be477937008c28)
- liguodongiot/llm-action: Read on November 16, 2026, at commit d33c2c0 (https://github.com/liguodongiot/llm-action/tree/d33c2c0f06e4d402c669bd57e6506955efbec9ff)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.
